Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.

01Result

alpic-ai/skybridge ↗

alpic-ai/skybridge AI coding statistics: 8.9%

of 372 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.9% agent · top contributor 39.4%10 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

33
agent commits
339
other considered commits
10
agent contributors
39.4%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

28assisted
5autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-024.3%69
2026-0314.1%64
2026-0411.9%42
2026-050%72
2026-067%43
2026-079.3%43
2026-0816%25
2026-0935.7%14

Peak month: 35.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic287.5%
Cursor AgentAnysphere51.3%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 8fd1fe87 on GitHubfix(evals): collect scenarios without the evals option and widen test peerClaude Code
  • 001284fa on GitHubfix(devtools): reset display mode on requestClose so modals can be dismissClaude Code
  • 15507fe7 on GitHubadded lightbulb to show some tips (#1080)Claude Code
  • da3047d4 on GitHubfix(devtools): size the view iframe to the whole document so short widgetsCursor Agent
  • 0f125795 on GitHubfeat!: migrate to @modelcontextprotocol/sdk v2 (MCP 2026-07-28) (#1008)Cursor Agent
  • bb11fe01 on GitHubfix(docs): add missing mcpcn showcase preview image (#1068)Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window433
Merge commits removed−0
CI / dependency bots removed−61
Considered372

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli alpic-ai/skybridge

Scan another repository

Try